paper-with-me

Papers

Reward-Centered ReST-MCTS: A Robust Decision-Making Framework for Robotic Manipulation in High Uncertainty Environments

2025-03-07 · Xibai Wang

Monte Carlo Tree Search (MCTS) has emerged as a powerful tool for decision-making in robotics, enabling efficient exploration of large search spaces. However, traditional MCTS methods struggle in environments characterized by high uncertainty and noisy data due to their reliance on final-step reward evaluation. The lack of intermediate feedback during search often results in suboptimal decision-making and computational inefficiencies. This paper introduces Reward-Centered ReST-MCTS, a novel framework that enhances MCTS by incorporating intermediate reward shaping. The core of our approach is the Rewarding Center, which refines search trajectories by dynamically assigning partial rewards using rule-based validation, heuristic guidance, and neural estimation. By integrating these mechanisms, our method enables real-time optimization of search paths, mitigating the effects of error propagation. We evaluate Reward-Centered ReST-MCTS in robotic manipulation tasks under high uncertainty, demonstrating consistent improvements in decision accuracy. Compared to baseline methods, including Chain-of-Thought (CoT) prompting and Vanilla ReST-MCTS, our framework achieves a 2-4% accuracy improvement while maintaining computational feasibility. Ablation studies confirm the effectiveness of intermediate feedback in search refinement, particularly in pruning incorrect decision paths early. Furthermore, robustness tests show that our method retains high performance across varying levels of uncertainty.

📄 PDF Abstract BibTeX arXiv:2503.05226

Code (1)

MilesTime/Reward-Centered-ReST-MCTS 공식 구현

Tasks

Decision MakingEfficient Exploration

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Optimized Monte Carlo Tree Search for Enhanced Decision Making in the FrozenLake Environment

2024-09-25 · Esteban Aldana Guerra

Monte Carlo Tree Search (MCTS) is a powerful algorithm for solving complex decision-making problems. This paper presents an optimized MCTS implementation applied to the FrozenLake environment, a classic reinforcement lea…

Decision MakingQ-Learning

Decision Making in Non-Stationary Environments with Policy-Augmented Monte Carlo Tree Search

2022-02-25 · Geoffrey Pettet, Ayan Mukhopadhyay, Abhishek Dubey

Decision-making under uncertainty (DMU) is present in many important problems. An open challenge is DMU in non-stationary environments, where the dynamics of the environment can change over time. Reinforcement Learning (…

Decision MakingDecision Making Under UncertaintyReinforcement Learning (RL)

Deep Learning for Reward Design to Improve Monte Carlo Tree Search in ATARI Games

2016-04-24 · Xiaoxiao Guo, Satinder Singh, Richard Lewis, Honglak Lee

Monte Carlo Tree Search (MCTS) methods have proven powerful in planning for sequential decision-making problems such as Go and video games, but their performance can be poor when the planning depth and sampling trajector…

Atari GamesDecision MakingSequential Decision Making

C-MCTS: Safe Planning with Monte Carlo Tree Search

2023-05-25 · Dinesh Parthasarathy, Georgios Kontes, Axel Plinge, Christopher Mutschler

The Constrained Markov Decision Process (CMDP) formulation allows to solve safety-critical decision making tasks that are subject to constraints. While CMDPs have been extensively studied in the Reinforcement Learning li…

Decision Making

ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search

2024-06-06 · Dan Zhang, Sining Zhoubian, Ziniu Hu, Yisong Yue 외

Recent methodologies in LLM self-training mostly rely on LLM generating responses and filtering those with correct output answers as training data. This approach often yields a low-quality fine-tuning training set (e.g.,…